Berget AI's System One model for gating agent commands: a LoRA adapter and a fine-tuned joint schema head on Cloudflare's Clef-Flash that answer noul, choice and score questions over a state in one forward pass. Trained on Swedish and English operations decisions.
Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations.
Decides
noul, choice, score
choice, score, noul, classify, extract, route
Architecture
clef
gliner2
Fine-tuned from
cloudflare/clef-flash
fastino/gliner2-large-v1
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Fastino
Input price
—
—
Decision accuracy
97.0%
60.2%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
38.3 ms
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between bev and gliner2-5-decide?
bev is from Berget AI and gliner2-5-decide from Fastino Labs. bev has open weights you can download and run; gliner2-5-decide has open weights and a hosted API. Both answer noul, choice and score questions. Only gliner2-5-decide answers classify, extract and route. gliner2-5-decide is the smaller model, at 340M parameters to 9.0B.
Which is more accurate, bev or gliner2-5-decide?
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev or gliner2-5-decide?
bev: Free (open weights). gliner2-5-decide: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run bev or gliner2-5-decide locally?
Yes, both: systemone pull berget-ai/bev and systemone pull fastino-labs/gliner2-5-decide download the weights.
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
